Powered by OpenAIRE graph
Found an issue? Give us feedback
https://dx.doi.org/1...arrow_drop_down
https://dx.doi.org/10.26262/he...
Other literature type . 2016
License: CC BY SA
Data sources: Datacite
addClaim

Βελτιστοποίηση γενικών συνδέσεων σε συστήματα Spark

Βελτιστοποίηση γενικών συνδέσεων σε συστήματα Spark

Abstract

Στην παρούσα εργασία, παρουσιάζουμε και εξετάζουμε τρόπους για την αποδοτικότερη εκτέλεση γενικών συνδέσεων σε ένα σύστημα Spark που επεκτείνει το προγραμματιστικό μοντέλο MapRecuce. Συγκεκριμένα, επικεντρωνόμαστε στη βελτιστοποίηση του ποσοστού του κόστους επικοινωνίας, που προκύπτει από την υλοποίηση γενικών συνδέσεων στο σύστημα Spark και στην αποδοτικότερη κατανομή του φόρτου εργασίας, που επηρεάζεται από τη διασπορά των δεδομένων μέσα σε ένα κατανεμημένο σύστημα. Παράλληλα εκτελούμε πειράματα σε μεγάλα σύνολα δεδομένων και παρουσιάζουμε τα ευρήματα, που δείχνουν το ποσοστό της βελτιστοποίησης που έχει επιτευχθεί. Τέλος, αναφέρουμε μία ολοκληρωμένη μεθοδολογία για την εισαγωγή δεδομένων σε ένα σύστημα Spark και τη χρήση των κατάλληλων τεχνικών για τη μείωση του κόστους επικοινωνίας κατά την εκτέλεση γενικών συνδέσεων.

In this work, we present and examine ways for a more efficient run of theta joins in a Spark system which extends the MapReduce programming model. Specifically, we focus on the optimization of the percentage of the communication cost, which occurs by performing theta joins in a Spark system and on the efficiency of the workload, which is affected by the dispersion of the data in a distributed system. Meanwhile, we conduct experiments in big sets of data and we present the findings, which show the optimization percentage that has been accomplished. Finally, we mention a methodology for inserting data in a Spark system and using appropriate techniques in order to reduce the communication cost that occurs during the execution of natural join tasks.

Keywords

Βελτιστοποίηση κόστους επικοινωνία, Apache Spark, Γενικές συνδέσεις, Optimization of communication cost, Theta-Joins

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!